@inproceedings{plank-2010-improved,
title = "Improved Statistical Measures to Assess Natural Language Parser Performance across Domains",
author = "Plank, Barbara",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/801_Paper.pdf",
abstract = "We examine the performance of three dependency parsing systems, in particular, their performance variation across Wikipedia domains. We assess the performance variation of (i) Alpino, a deep grammar-based system coupled with a statistical disambiguation versus (ii) MST and Malt, two purely data-driven statistical dependency parsing systems. The question is how the performance of each parser correlates with simple statistical measures of the text (e.g. sentence length, unknown word rate, etc.). This would give us an idea of how sensitive the different systems are to domain shifts, i.e. which system is more in need for domain adaptation techniques. To this end, we extend the statistical measures used by Zhang and Wang (2009) for English and evaluate the systems on several Wikipedia domains by focusing on a freer word-order language, Dutch. The results confirm the general findings of Zhang and Wang (2009), i.e. different parsing systems have different sensitivity against various statistical measure of the text, where the highest correlation to parsing accuracy was found for the measure we added, sentence perplexity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plank-2010-improved">
<titleInfo>
<title>Improved Statistical Measures to Assess Natural Language Parser Performance across Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We examine the performance of three dependency parsing systems, in particular, their performance variation across Wikipedia domains. We assess the performance variation of (i) Alpino, a deep grammar-based system coupled with a statistical disambiguation versus (ii) MST and Malt, two purely data-driven statistical dependency parsing systems. The question is how the performance of each parser correlates with simple statistical measures of the text (e.g. sentence length, unknown word rate, etc.). This would give us an idea of how sensitive the different systems are to domain shifts, i.e. which system is more in need for domain adaptation techniques. To this end, we extend the statistical measures used by Zhang and Wang (2009) for English and evaluate the systems on several Wikipedia domains by focusing on a freer word-order language, Dutch. The results confirm the general findings of Zhang and Wang (2009), i.e. different parsing systems have different sensitivity against various statistical measure of the text, where the highest correlation to parsing accuracy was found for the measure we added, sentence perplexity.</abstract>
<identifier type="citekey">plank-2010-improved</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/801_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improved Statistical Measures to Assess Natural Language Parser Performance across Domains
%A Plank, Barbara
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F plank-2010-improved
%X We examine the performance of three dependency parsing systems, in particular, their performance variation across Wikipedia domains. We assess the performance variation of (i) Alpino, a deep grammar-based system coupled with a statistical disambiguation versus (ii) MST and Malt, two purely data-driven statistical dependency parsing systems. The question is how the performance of each parser correlates with simple statistical measures of the text (e.g. sentence length, unknown word rate, etc.). This would give us an idea of how sensitive the different systems are to domain shifts, i.e. which system is more in need for domain adaptation techniques. To this end, we extend the statistical measures used by Zhang and Wang (2009) for English and evaluate the systems on several Wikipedia domains by focusing on a freer word-order language, Dutch. The results confirm the general findings of Zhang and Wang (2009), i.e. different parsing systems have different sensitivity against various statistical measure of the text, where the highest correlation to parsing accuracy was found for the measure we added, sentence perplexity.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/801_Paper.pdf
Markdown (Informal)
[Improved Statistical Measures to Assess Natural Language Parser Performance across Domains](http://www.lrec-conf.org/proceedings/lrec2010/pdf/801_Paper.pdf) (Plank, LREC 2010)
ACL